Publications

Review publications from the AuroraGPT team.

Extending µP: Spectral Conditions for Feature Learning Across Optimizers

Gupta, A., Ngom, M., Foreman, S., and Vishwanath, W.

Optimization for Machine Learning Workshop at the Conference on Neural Information Processing Systems (NeurIPS), 2025
Submitted to International Conference on Learning Representations 2026

LSHBloom: Internet-Scale Text Deduplication

Khan, A., Underwood, R., Seibenshuh, C., Babuji, Y., Ajith, A., et al.

PrePrint

ChemGraph: An Agentic Framework for Computational Chemistry Workflows

Pham, T. D., Tanikanti, A., and Keçeli, M.

Communications Chemistry, 2026

Probing the Critical Point (CritPt) of AI Reasoning: A Frontier Physics Research Benchmark

Zhu, M., Tian, M., Yang, X., Zhou, T., Yuan, L., Zhu, P., et al.

Project Report, 2025

Automated MCQA Benchmarking at Scale: Evaluating Reasoning Traces as Retrieval Sources for Domain Adaptation of Small Language Models

Gokdemir, O., Getty, N., Underwood, R., Madireddy, S., Cappello, F., et al.

Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC25) Workshops, 2025

Beyond End-to-End: Understanding the Limits of LLMs in Scientific Problem Solving

Liu, Y., Di, S., Getty, N., Mallick, T., Underwood, R., and Jin, S.

Frontiers in Generative AI for HPC Science and Engineering: Foundations, Challenges, and Opportunities.
Trillion Parameter Consortium at The International Conference for High Performance Computing, Networking, Storage, and Analysis (TPC@SC), 2025

Evaluation of Test-Time Compute Constraints on Safety and Skill Large Reasoning Models

A. Balaji, L. Chen, R. Thakur, F. Cappello, and S. Madireddy.

Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC25) Workshops, 2025

FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access

Tanikanti, A., Côté, B., Guo, Y., Chen, L., Saint, N., Chard, R., Raffenetti, K., et al.

Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC25) Workshops, 2025

Exploring Distributed Vector Databases Performance on HPC Platforms: A Study with Qdrant

Ockerman, S., Gueroudji, A., Oh, S. Y., Underwood, R., Chia, N., Chard, K., Ross, R., and Venkataraman, S.

Frontiers in Generative AI for HPC Science and Engineering: Foundations, Challenges, and Opportunities
Trillion Parameter Consortium at The International Conference for High Performance Computing, Networking, Storage, and Analysis (TPC@SC), 2025

Context Length Alone Hurts LLM Performance Despite Perfect Retrieval

Y. Du, M. Tian, S. Ronanki, S. Rongali, S. Bodapati, A. Galstyan, A. Wells, R. Schwartz, E. Huerta, and H. Peng.

Empirical Methods in Natural Language Processing (EMNLP), 2025

Evaluating the Safety and Skill Reasoning of Large Reasoning Models Under Compute Constraints

A. Balaji, L. Chen, R. Thakur, F. Cappello, and S. Madireddy

First Workshop on Efficient Reasoning, Neural Information Processing Systems (NeurIPS), 2025

AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions

V. Hatanpää, E. Ku, J. Stock, M. Emani, S. Foreman, C. Jung, S. Madireddy, et al.

2025

Teaching LLMs to Speak Spectroscopy

Ramachandra, N. S., Ting, Y.-S., Sun, Z., Wells, A., and Habib, S.

Machine Learning for Astrophysics Workshop
International Conference on Machine Learning (ICML), 2025

UProp: Investigating the Uncertainty Propagation of LLMs in Multi-step Agentic Decision-making

Duan, J., Diffenderfer, J., Madireddy, S., Chen, T., Kailkhura, B., and Xu, K.

arXiv preprint arXiv:2506.17419, 2025

HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights

Gokdemir, O., Siebenschuh, C., Brace, A., Wells, A., Hsu, B., Hippe, K., et al.

Proceedings of the Platform for Advanced Scientific Computing Conference (PASC '25)

AstroSage: Leading Performance in Astronomy Q&A with a 70B-parameter Domain-specialized Model

de Haan, T., Ting, Y.-S., Ghosal, T., Nguyen, J., Accomazzi, A., Herron, E., et al.

Machine Learning for Astrophysics Workshop
International Conference on Machine Learning (ICML), 2025

AdaParse: An Adaptive Parallel {PDF} Parsing and Resource Scaling Engine

Siebenschuh, C., Hippe, K., Gokdemir, O., Brace, A., Khan, A., Hossain, K., et al.

Eighth Conference on Machine Learning and Systems (MLSys), 2025

AstroMLab 1: Who Wins Astronomy Jeopardy!?

Ting, Y.-S., Nguyen, T. D., Ghosal, T., Pan, R., Arora, H., Sun, Z., de Haan, T., et al.

Astronomy and Computing, 2025

EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants

Cappello, F., Madireddy, S., Underwood, R., Getty, N., Chia, N., Ramachandra, N., et al.

arXiv preprint arXiv:2502.20309, 2025

Scaling Large Vision-Language Models for Enhanced Multimodal Comprehension in Biomedical Image Analysis

Umeike, R., Getty, N., Xia, F., and Stevens, R.

IEEE 22nd International Symposium on Biomedical Imaging (ISBI), 2025.

Benchmarking Large Language Models for Materials Synthesis: The Case of Atomic Layer Deposition

Yanguas-Gil, A., Dearing, M. T., Elam, J. W., Jones, J. C., Kim, S., Mohammad, A., Nguyen, C. T., and Sengupta, B.

Journal of Vacuum Science & Technology A, 2025

MProt-DPO: Breaking the ExaFLOPS Barrier for Multimodal Protein Design Workflows with Direct Preference Optimization

Dharuman, G., Hippe, K., Brace, A., Foreman, S., Hatanpää, V., Sastry, V. K., et al.

International Conference for High Performance Computing, Networking, Storage and Analysis (SC24), 2024

Quantifying Uncertainty in Large Language Models: Applications in Molecular Chemistry Tasks

Chen, Z., Hong, P., and Madireddy, S.

Workshop on Statistical Foundations of LLMs and Foundation Models, Advances in Neural Information Processing Systems (NeurIPS), 2024

SciCode: A Research Coding Benchmark Curated by Scientists

Tian, M., Gao, L., Zhang, S. D., Chen, X., Fan, C., Guo, X., et al.

Advances in Neural Information Processing Systems (NeurIPS) — Datasets & Benchmarks Track, 2024

Toward a Holistic Performance Evaluation of Large Language Models Across Diverse AI Accelerators

Emani, M., Foreman, S., Sastry, V., Xie, Z., Raskar, S., Arnold, W., et al.

IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2024

Thorough Characterization and Analysis of Large Transformer Model Training At-Scale

Cheng, S., Lin, J.-L., Emani, M., Raskar, S., Foreman, S., Xie, Z., Vishwanath, V., and Kandemir, M. T.

Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2024